OCNet: Object Context Network for Scene Parsing

In this paper, we address the semantic segmentation task with a new context aggregation scheme named \emph{object context}, which focuses on enhancing the role of object information. Motivated by the fact that the category of each pixel is inherited from the object it belongs to, we define the object context for each pixel as the set of pixels that belong to the same category as the given pixel in the image... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Segmentation Cityscapes test OCNet Mean IoU (class) 81.7% # 28

Methods used in the Paper


METHOD TYPE
ReLU
Activation Functions
Batch Normalization
Normalization
Convolution
Convolutions
Average Pooling
Pooling Operations
Pyramid Pooling Module
Semantic Segmentation Modules
Auxiliary Classifier
Miscellaneous Components
Dilated Convolution
Convolutions
PSPNet
Semantic Segmentation Models